Qwen3.8 Max (0902) vs Inkling Small
Updated October 21, 2026. 80 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Qwen3.8 Max (0902) for coding: it scores 63.5 on the Vibe Coding Index against 29.9 for Inkling Small.
Pick Inkling Small when output tokens cost 5.0x less, or when a solved task costs $0.16 against $1.32.
- Shared results
- 80
- Qwen3.8 Max (0902) only
- 33
- Inkling Small only
- 4
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) scores 63.5 against 29.9.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 45.4 against 25.7.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 56.0 against 23.5.
Same board, both measured
Reasoning
GPQA Diamond
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 93.7% against 83.6%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 88.6% against 85.6%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3.8 Max (0902) has a Design Arena: websites result, 1275.
Directional only
General
Vals Index
No call
Only Inkling Small has a Vals Index result, 27.6%.
Directional only
Long documents
Listed context window
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) takes 1M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling Small
Qwen3.8 Max (0902) $0.0050, Inkling Small $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Inkling Small
Qwen3.8 Max (0902) $1.32, Inkling Small $0.16.
Published attempt cost and pass rate
At a glance
- Coding index
- Qwen3.8 Max (0902) 63.5 from 2 benchmarks, Inkling Small 29.9 from 1 benchmark.
- Widest category
- Math, 22.5 points apart on average over 6 shared benchmarks.
- Widest single gap
- IOI (Vals AI): Qwen3.8 Max (0902) 68.9% against Inkling Small 9.3%, 59.6 points apart on a 0 to 100 scale.
- Output price
- Qwen3.8 Max (0902) $6.00 against Inkling Small $1.20 per million output tokens, 5.0x apart.
- Context window
- Qwen3.8 Max (0902) takes 1M tokens, Inkling Small 524K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Qwen3.8 Max (0902) | Bars | Inkling Small | Ties |
|---|---|---|---|---|
| Coding | 16 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 0 | ||
| Reasoning | 10 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 10 | 1 | ||
| General | 28 | 0 | ||
| All shared boards | 77 | 3 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index162
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| LiveBench coding | 60.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena WebDev | 1674 | 1409 | Qwen3.8 Max (0902) |
| AA Coding Index | 76.2 | 52.9 | Qwen3.8 Max (0902) |
| LiveCodeBench (Vals AI) | 87.8% | 85.9% | Qwen3.8 Max (0902) |
| SWE-bench Verified (Vals AI) | 85.6% | 82.2% | Qwen3.8 Max (0902) |
| Terminal-Bench 4 (Vals AI) | 34.3% | 0.0% | Qwen3.8 Max (0902) |
| Vibe Code Bench (Vals AI) | 64.7% | 19.1% | Qwen3.8 Max (0902) |
| Code migration (Vals AI) | 24.0% | 13.7% | Qwen3.8 Max (0902) |
| ProgramBench (Vals AI) | 0.0% | 0.5% | Inkling Small |
| IOI (Vals AI) | 68.9% | 9.3% | Qwen3.8 Max (0902) |
| Terminal-Bench 2.1 (Vals AI) | 67.4% | 55.1% | Qwen3.8 Max (0902) |
| SWE-bench Multimodal (Vals AI) | 42.5% | Not measured | Only Qwen3.8 Max (0902) measured |
| Vibe Code Bench 1-100 (Vals AI) | 12.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| SkillsBench (Vals AI) | 42.0% | 33.6% | Qwen3.8 Max (0902) |
| CyberBench (Vals AI) | 28.6% | 64.1% | Inkling Small |
| SciCode | 53.2% | 49.7% | Qwen3.8 Max (0902) |
| FrontierSWE | 17.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: coding | 1502 | 1450 | Qwen3.8 Max (0902) |
| LMArena Text: software and IT | 1498 | 1447 | Qwen3.8 Max (0902) |
| LMArena WebDev: React | 1692 | 1399 | Qwen3.8 Max (0902) |
| LMArena WebDev: HTML | 1649 | 1398 | Qwen3.8 Max (0902) |
| LMArena WebDev: from an image | 1637 | 1410 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 45.4 | 25.7 | Qwen3.8 Max (0902) |
| Epoch Capabilities Index | 157.4 | 150.3 | Qwen3.8 Max (0902) |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| AA Agentic Index | 56.0 | 23.5 | Qwen3.8 Max (0902) |
| Design Arena: agents building web apps | 1301 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building full-stack apps | 1305 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building mobile apps | 1223 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Android apps | 1207 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Godot games | 1234 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: PowerPoint slides | 1257 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: spreadsheets | 868 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench research | 69.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench browser | 32.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench long agentic | 42.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| Finance Agent (Vals AI) | 50.6% | 41.3% | Qwen3.8 Max (0902) |
| Tax Agent Bench (Vals AI) | 32.1% | 15.4% | Qwen3.8 Max (0902) |
| Legal Research Bench (Vals AI) | 47.6% | 25.5% | Qwen3.8 Max (0902) |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 2.9% | Only Inkling Small measured |
| Excel Modeling Benchmark (Vals AI) | 60.1% | 31.8% | Qwen3.8 Max (0902) |
| Terminal-Bench-Science (Vals AI) | 12.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| APEX-Agents | 63.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Search | 1261 | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| GPQA Diamond | 93.7% | 83.6% | Qwen3.8 Max (0902) |
| LiveBench reasoning | 88.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| MysteryMechanism (Vals AI) | 23.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| MMMU Pro (Vals AI) | 88.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| GPQA Diamond (Artificial Analysis run) | 92.8% | 89.5% | Qwen3.8 Max (0902) |
| Humanity's Last Exam (Artificial Analysis run) | 43.1% | 33.3% | Qwen3.8 Max (0902) |
| GPQA Diamond (Epoch AI run) | 92.7% | 88.5% | Qwen3.8 Max (0902) |
| ARC-AGI | Not measured | 84.0% | Only Inkling Small measured |
| ARC-AGI-2 | Not measured | 40.1% | Only Inkling Small measured |
| Chess puzzles | 46.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Mystery game puzzles | 38.0% | 6.0% | Qwen3.8 Max (0902) |
| LMArena Text: hard prompts | 1496 | 1423 | Qwen3.8 Max (0902) |
| LMArena Text: expert | 1507 | 1441 | Qwen3.8 Max (0902) |
| LMArena Text: hard prompts in English | 1503 | 1429 | Qwen3.8 Max (0902) |
| LMArena Vision: diagrams | 1323 | 1251 | Qwen3.8 Max (0902) |
| LMArena Vision: homework | 1336 | 1257 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 90.0% | Qwen3.8 Max (0902) |
| FrontierMath, tiers 1 to 3 | 74.7% | 46.3% | Qwen3.8 Max (0902) |
| FrontierMath, tier 4 | 46.3% | 17.1% | Qwen3.8 Max (0902) |
| ProofBench | 58.0% | 6.0% | Qwen3.8 Max (0902) |
| LMArena Text: math | 1501 | 1459 | Qwen3.8 Max (0902) |
| LMArena Text: mathematical work | 1491 | 1441 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| MMLU Pro | 88.6% | 85.6% | Qwen3.8 Max (0902) |
| LegalBench (Vals AI) | 83.6% | 83.0% | Qwen3.8 Max (0902) |
| CorpFin (Vals AI) | 65.8% | 69.6% | Inkling Small |
| TaxEval (Vals AI) | 75.5% | 75.5% | Qwen3.8 Max (0902) |
| MortgageTax (Vals AI) | 64.0% | 62.3% | Qwen3.8 Max (0902) |
| MedCode (Vals AI) | 40.7% | 37.9% | Qwen3.8 Max (0902) |
| SimpleQA Verified | 47.3% | 19.1% | Qwen3.8 Max (0902) |
| LMArena Text: science | 1512 | 1428 | Qwen3.8 Max (0902) |
| LMArena Text: medicine and healthcare | 1503 | 1413 | Qwen3.8 Max (0902) |
| LMArena Text: legal and government | 1492 | 1415 | Qwen3.8 Max (0902) |
| LMArena Text: business and finance | 1480 | 1413 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1275 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: UI components | 1340 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: game dev | 1313 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: data viz | 1281 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: 3D | 1337 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: all code categories | 1293 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: ASCII art | 1201 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench design | 78.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index280
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| Vals Index | Not measured | 27.6% | Only Inkling Small measured |
| LiveBench data analysis | 78.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| Public Benefits Bench (Vals AI) | 67.1% | 59.4% | Qwen3.8 Max (0902) |
| SAGE (Vals AI) | 51.2% | 32.7% | Qwen3.8 Max (0902) |
| MedScribe (Vals AI) | 85.0% | 84.1% | Qwen3.8 Max (0902) |
| Vals Multimodal Index | 65.4% | 50.0% | Qwen3.8 Max (0902) |
| Long context reasoning (AA-LCR) | 80.3% | 75.7% | Qwen3.8 Max (0902) |
| DTBench | 92.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMCA | 46.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| Furniture assembly | 20.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text | 1483 | 1413 | Qwen3.8 Max (0902) |
| LMArena Text: instruction following | 1481 | 1399 | Qwen3.8 Max (0902) |
| LMArena Text: creative writing | 1477 | 1334 | Qwen3.8 Max (0902) |
| LMArena Vision | 1313 | 1237 | Qwen3.8 Max (0902) |
| LMArena Text: English | 1491 | 1421 | Qwen3.8 Max (0902) |
| LMArena Text: non-English | 1473 | 1401 | Qwen3.8 Max (0902) |
| LMArena Text: Chinese | 1539 | 1464 | Qwen3.8 Max (0902) |
| LMArena Text: German | 1478 | 1408 | Qwen3.8 Max (0902) |
| LMArena Text: Japanese | 1473 | 1401 | Qwen3.8 Max (0902) |
| LMArena Text: Korean | 1460 | 1367 | Qwen3.8 Max (0902) |
| LMArena Text: French | 1498 | 1435 | Qwen3.8 Max (0902) |
| LMArena Text: Spanish | 1489 | 1422 | Qwen3.8 Max (0902) |
| LMArena Text: Russian | 1482 | 1394 | Qwen3.8 Max (0902) |
| LMArena Text: Polish | 1471 | 1428 | Qwen3.8 Max (0902) |
| LMArena Text: multi-turn | 1489 | 1416 | Qwen3.8 Max (0902) |
| LMArena Text: longer queries | 1488 | 1402 | Qwen3.8 Max (0902) |
| LMArena Text: writing and language | 1477 | 1357 | Qwen3.8 Max (0902) |
| LMArena Text: entertainment and media | 1464 | 1352 | Qwen3.8 Max (0902) |
| LMArena Vision: English | 1311 | 1243 | Qwen3.8 Max (0902) |
| LMArena Vision: Chinese | 1358 | 1292 | Qwen3.8 Max (0902) |
| LMArena Vision: reading text | 1322 | 1243 | Qwen3.8 Max (0902) |
| LMArena Vision: humor | 1304 | 1207 | Qwen3.8 Max (0902) |
| LMArena Vision: creative writing | 1312 | 1205 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Inkling Small | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Inkling Small costs less
Repository review
50K input + 3K output tokens
Inkling Small costs less
Agent loop
200K input + 10K output tokens
Inkling Small costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Qwen3.8 Max (0902) | Thinking Machines Inkling Small |
|---|---|---|
| Maker | Qwen | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | September 3, 2026 | July 30, 2026 |
| Context window | 1M | 524K |
| Input $/Mtok | $2.00 | $0.45 |
| Output $/Mtok | $6.00 | $1.20 |
| Coding index | 63.5 | 29.9 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $1.32 | $0.16 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.8 Max (0902) better than Inkling Small for coding?
Pick Qwen3.8 Max (0902) for coding: it scores 63.5 on the Vibe Coding Index against 29.9 for Inkling Small. Pick Inkling Small when output tokens cost 5.0x less, or when a solved task costs $0.16 against $1.32.
Which is cheaper, Qwen3.8 Max (0902) or Inkling Small?
Qwen3.8 Max (0902) costs $2.00 per million input tokens and $6.00 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, Qwen3.8 Max (0902) costs $1.32 and Inkling Small $0.16.
Which has the bigger context window, Qwen3.8 Max (0902) or Inkling Small?
Qwen3.8 Max (0902), with 1M tokens against 524K.
How many benchmarks is the Qwen3.8 Max (0902) vs Inkling Small comparison based on?
80 benchmarks have a result for both models as of October 21, 2026. Qwen3.8 Max (0902)'s coding index rests on 2 independent benchmarks and Inkling Small's on 1. Where only one model has a result, the page says so instead of naming a winner.